Triple
T28410401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | annona (Roman grain supply system) |
E719646
|
entity |
| Predicate | notableEmperorInvolved |
P35965
|
FINISHED |
| Object | Augustus |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Augustus | Statement: [annona (Roman grain supply system), notableEmperorInvolved, Augustus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableEmperorInvolved Context triple: [annona (Roman grain supply system), notableEmperorInvolved, Augustus]
-
A.
notableEmperorPersonalName
Indicates that the object is the personal (given) name of an emperor who is historically notable.
-
B.
hasNotableEmperor
chosen
Indicates that an entity is associated with at least one emperor who is historically recognized as particularly important or distinguished.
-
C.
notableKingMentionedBySources
Indicates that historical or authoritative sources explicitly mention the king as being notable or significant.
-
D.
notableRulerDuringService
Indicates that a specified ruler was notably in power during the time an entity (such as a person or organization) was active or providing service.
-
E.
hasEmperor
Indicates that an entity is ruled or governed by an emperor.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69eff6f0f37c8190b37bc6fab08a9449 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_6a00d8ba18808190976682088a02a9a8 |
completed | May 10, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_6a00d85fad64819084f424ec8ecd3b57 |
completed | May 10, 2026, 7:11 p.m. |
Created at: April 28, 2026, 1:26 a.m.